ppo-Huggy / run_logs /timers.json
achupakhin's picture
Huggy
6f9d8df verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401136875152588,
"min": 1.401136875152588,
"max": 1.4284316301345825,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70747.6015625,
"min": 68601.1484375,
"max": 75624.5078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.04040404040404,
"min": 88.71633752244165,
"max": 390.6015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49520.0,
"min": 48908.0,
"max": 50085.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49570.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49570.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.412029504776001,
"min": 0.0381278358399868,
"max": 2.42240834236145,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1193.95458984375,
"min": 4.842235088348389,
"max": 1310.52294921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7058899850556344,
"min": 1.7824638119832736,
"max": 3.96908415847173,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1834.415542602539,
"min": 226.37290412187576,
"max": 2129.5544633865356,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7058899850556344,
"min": 1.7824638119832736,
"max": 3.96908415847173,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1834.415542602539,
"min": 226.37290412187576,
"max": 2129.5544633865356,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016849361885882295,
"min": 0.013729928632771286,
"max": 0.019808220463649683,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05054808565764688,
"min": 0.02745985726554257,
"max": 0.05536888496717438,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050071641016337605,
"min": 0.021526340084771313,
"max": 0.06013245984084076,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15021492304901282,
"min": 0.043052680169542626,
"max": 0.18039737952252227,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.467698844133325e-06,
"min": 3.467698844133325e-06,
"max": 0.000295355476548175,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0403096532399975e-05,
"min": 1.0403096532399975e-05,
"max": 0.000844311018563,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115586666666665,
"min": 0.10115586666666665,
"max": 0.19845182499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30346759999999995,
"min": 0.2075014,
"max": 0.5814370000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.767774666666656e-05,
"min": 6.767774666666656e-05,
"max": 0.004922746067500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002030332399999997,
"min": 0.0002030332399999997,
"max": 0.014073706299999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1732632499",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732635293"
},
"total": 2793.927660792,
"count": 1,
"self": 0.48942666400034796,
"children": {
"run_training.setup": {
"total": 0.0680767480000668,
"count": 1,
"self": 0.0680767480000668
},
"TrainerController.start_learning": {
"total": 2793.37015738,
"count": 1,
"self": 5.288906393948764,
"children": {
"TrainerController._reset_env": {
"total": 6.837488815000029,
"count": 1,
"self": 6.837488815000029
},
"TrainerController.advance": {
"total": 2781.115472427051,
"count": 231789,
"self": 5.328623849037285,
"children": {
"env_step": {
"total": 2226.701032504007,
"count": 231789,
"self": 1758.5521783751033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 464.7548376749479,
"count": 231789,
"self": 17.333202017958115,
"children": {
"TorchPolicy.evaluate": {
"total": 447.4216356569898,
"count": 223050,
"self": 447.4216356569898
}
}
},
"workers": {
"total": 3.394016453955828,
"count": 231789,
"self": 0.0,
"children": {
"worker_root": {
"total": 2785.3097856110135,
"count": 231789,
"is_parallel": true,
"self": 1356.3864855751149,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009356439999237409,
"count": 1,
"is_parallel": true,
"self": 0.0002501979997759918,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006854460001477491,
"count": 2,
"is_parallel": true,
"self": 0.0006854460001477491
}
}
},
"UnityEnvironment.step": {
"total": 0.03356799499999852,
"count": 1,
"is_parallel": true,
"self": 0.00047225799994521367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002078700000538447,
"count": 1,
"is_parallel": true,
"self": 0.0002078700000538447
},
"communicator.exchange": {
"total": 0.03203467200000887,
"count": 1,
"is_parallel": true,
"self": 0.03203467200000887
},
"steps_from_proto": {
"total": 0.0008531949999905919,
"count": 1,
"is_parallel": true,
"self": 0.00024781000001894427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006053849999716476,
"count": 2,
"is_parallel": true,
"self": 0.0006053849999716476
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1428.9233000358986,
"count": 231788,
"is_parallel": true,
"self": 42.968069078602184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.3235822421293,
"count": 231788,
"is_parallel": true,
"self": 91.3235822421293
},
"communicator.exchange": {
"total": 1191.7148866530931,
"count": 231788,
"is_parallel": true,
"self": 1191.7148866530931
},
"steps_from_proto": {
"total": 102.91676206207399,
"count": 231788,
"is_parallel": true,
"self": 36.23068235506753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.68607970700646,
"count": 463576,
"is_parallel": true,
"self": 66.68607970700646
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 549.0858160740065,
"count": 231789,
"self": 8.156797683957734,
"children": {
"process_trajectory": {
"total": 187.6503092320478,
"count": 231789,
"self": 186.12231709204843,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5279921399993555,
"count": 10,
"self": 1.5279921399993555
}
}
},
"_update_policy": {
"total": 353.278709158001,
"count": 97,
"self": 282.9369467279995,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.3417624300015,
"count": 2910,
"self": 70.3417624300015
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3109997780702543e-06,
"count": 1,
"self": 1.3109997780702543e-06
},
"TrainerController._save_models": {
"total": 0.12828843300030712,
"count": 1,
"self": 0.0022004460001880943,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12608798700011903,
"count": 1,
"self": 0.12608798700011903
}
}
}
}
}
}
}